Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation

Documenti analoghi

• MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation
  di: Zhang, Ronyu, et al.
  Pubblicazione: (2026)
• T-REX: Mixture-of-Rank-One-Experts with Semantic-aware Intuition for Multi-task Large Language Model Finetuning
  di: Zhang, Rongyu, et al.
  Pubblicazione: (2024)
• MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation
  di: Zhang, Rongyu, et al.
  Pubblicazione: (2025)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models
  di: Zhao, Zhongyu, et al.
  Pubblicazione: (2024)
• BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection
  di: Zhang, Rongyu, et al.
  Pubblicazione: (2025)